Koskamo

CUBBY HOUSE MCP

An MCP server providing AI agents with access to an Australian mattress commerce platform. It enables agents to search products, match user sleep profiles to mattresses, retrieve retailer traction data, and submit qualified leads to retailers like OZ Design and Emma Sleep.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

CUBBY HOUSE MCP logo, by ML-NIGHTWORXCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by ML-NIGHTWORX
MCP endpoint (Streamable HTTP)
https://dome.ml-nightworx.io/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (4)

4 of 4 have a description · 0 of 4 declare behavior hints · 0 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for mattresses based on user criteria
  • Match sleep profiles to suitable products
  • Retrieve retailer traction data
  • Submit qualified shopper leads

Source and maintenance

Community listingRegistry 1.0.0
mcp-registry: io.github.GIT-access-ntwx/cubby-house@1.0.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
cubby-house-marketplace 1.0.0
MCP protocol negotiated in check
2024-11-05
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {}
}

Tools

4 advertised

dome_search_products
Advertised by the server during the last successful anonymous check.

Search the CUBBY HOUSE Australian mattress catalogue (14 retailers, 145 products). Params: q (keyword), retailer, size, min_price, max_price, firmness_min, firmness_max, sort (price_asc|price_desc|name), limit, offset.

dome_search_products input schema
{
  "type": "object",
  "properties": {
    "q": {
      "type": "string"
    },
    "size": {
      "type": "string"
    },
    "sort": {
      "enum": [
        "price_asc",
        "price_desc",
        "name"
      ],
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "maximum": 100
    },
    "offset": {
      "type": "integer"
    },
    "retailer": {
      "type": "string"
    },
    "max_price": {
      "type": "number"
    },
    "min_price": {
      "type": "number"
    },
    "firmness_max": {
      "type": "number"
    },
    "firmness_min": {
      "type": "number"
    }
  }
}
dome_match_profile
Advertised by the server during the last successful anonymous check.

Match a structured sleep profile to ranked products. Params: sleep_position (string|array: side|back|stomach|combination), pain_points (string|array: lower back pain|shoulder pain|hot sleeper|...), budget_min, budget_max (AUD), size, firmness (1-10), cooling_priority (bool|1-5), limit. Returns ranked matches with confidence + reasons + affiliate_url.

dome_match_profile input schema
{
  "type": "object",
  "required": [
    "sleep_position"
  ],
  "properties": {
    "size": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "maximum": 20
    },
    "firmness": {
      "type": "number"
    },
    "budget_max": {
      "type": "number"
    },
    "budget_min": {
      "type": "number"
    },
    "pain_points": {},
    "sleep_position": {},
    "cooling_priority": {}
  }
}
dome_get_retailer_traction
Advertised by the server during the last successful anonymous check.

Live retailer engagement traction: catalogue size per retailer plus outbound click volume in the recent window. Use to weight which retailers to surface first.

dome_get_retailer_traction input schema
{
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 20
    }
  }
}
dome_submit_lead
Advertised by the server during the last successful anonymous check.

Submit a qualified shopper lead into the CUBBY HOUSE pipeline (stored in Firestore, ops-notified, exportable by the operator). Params: name, email, message, product_id (optional), agent_id (your agent identity), ref_tag (optional).

dome_submit_lead input schema
{
  "type": "object",
  "required": [
    "name",
    "email"
  ],
  "properties": {
    "name": {
      "type": "string"
    },
    "email": {
      "type": "string"
    },
    "message": {
      "type": "string"
    },
    "ref_tag": {
      "type": "string"
    },
    "agent_id": {
      "type": "string"
    },
    "product_id": {
      "type": "string"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
1008 ms
95th percentile latency
1008 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 1008 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http cubby-house-mcp https://dome.ml-nightworx.io/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add cubby-house-mcp --url https://dome.ml-nightworx.io/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable cubby-house-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "cubby-house-mcp": {
      "url": "https://dome.ml-nightworx.io/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "cubby-house-mcp": {
      "type": "streamableHttp",
      "url": "https://dome.ml-nightworx.io/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start cubby-house-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "cubby-house-mcp": {
      "type": "http",
      "url": "https://dome.ml-nightworx.io/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http cubby-house-mcp https://dome.ml-nightworx.io/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://dome.ml-nightworx.io/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "cubby-house-mcp": {
      "serverUrl": "https://dome.ml-nightworx.io/mcp"
    }
  }
}

Let your agent find its tools

Find servers like CUBBY HOUSE MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 1,476